[PATCH v3 06/13] WIP: mm: hugetlb: Move subpool functions to hugetlb_subpool.c

[Ackerley Tng via B4 Relay]

From: Ackerley Tng <ackerleytng@xxxxxxxxxx>

Move all HugeTLB subpool lifecycle, page reservation, and accounting routines
out of `mm/hugetlb.c` and into their own dedicated, encapsulated translation unit
at `mm/hugetlb_subpool.c`.

Also introduces the internal `mm/hugetlb_subpool.h` header for holding the
subpool-local APIs, allowing `fs/hugetlbfs` and `mm/` to access the subpool functions cleanly.
The subpool internal layout structures remain in `include/linux/hugetlb.h` until getters
are introduced.

Signed-off-by: Ackerley Tng <ackerleytng@xxxxxxxxxx>
---
 fs/hugetlbfs/inode.c    |   1 +
 include/linux/hugetlb.h |   4 +-
 mm/Makefile             |   2 +-
 mm/hugetlb.c            | 156 +-------------------------------------------
 mm/hugetlb_subpool.c    | 168 ++++++++++++++++++++++++++++++++++++++++++++++++
 mm/hugetlb_subpool.h    |  17 +++++
 6 files changed, 191 insertions(+), 157 deletions(-)

diff --git a/fs/hugetlbfs/inode.c b/fs/hugetlbfs/inode.c
index 26c0187340636..8c1caad74c409 100644
--- a/fs/hugetlbfs/inode.c
+++ b/fs/hugetlbfs/inode.c
@@ -25,6 +25,7 @@
 #include <linux/ctype.h>
 #include <linux/backing-dev.h>
 #include <linux/hugetlb.h>
+#include "../../mm/hugetlb_subpool.h"
 #include <linux/folio_batch.h>
 #include <linux/fs_parser.h>
 #include <linux/mman.h>
diff --git a/include/linux/hugetlb.h b/include/linux/hugetlb.h
index 34b9a3e1be0fa..f36be371c6e88 100644
--- a/include/linux/hugetlb.h
+++ b/include/linux/hugetlb.h
@@ -114,9 +114,7 @@ extern int hugetlb_max_hstate __read_mostly;
 #define for_each_hstate(h) \
 	for ((h) = hstates; (h) < &hstates[hugetlb_max_hstate]; (h)++)
 
-struct hugepage_subpool *hugepage_new_subpool(struct hstate *h, long max_hpages,
-						long min_hpages);
-void hugepage_put_subpool(struct hugepage_subpool *spool);
+int hugetlb_acct_memory(struct hstate *h, long delta);
 
 void hugetlb_dup_vma_private(struct vm_area_struct *vma);
 void clear_vma_resv_huge_pages(struct vm_area_struct *vma);
diff --git a/mm/Makefile b/mm/Makefile
index eff9f9e7e061c..3965c959e5099 100644
--- a/mm/Makefile
+++ b/mm/Makefile
@@ -78,7 +78,7 @@ endif
 obj-$(CONFIG_SWAP)	+= page_io.o swap_state.o swapfile.o
 obj-$(CONFIG_ZSWAP)	+= zswap.o
 obj-$(CONFIG_HAS_DMA)	+= dmapool.o
-obj-$(CONFIG_HUGETLBFS)	+= hugetlb.o hugetlb_sysfs.o hugetlb_sysctl.o
+obj-$(CONFIG_HUGETLBFS)	+= hugetlb.o hugetlb_subpool.o hugetlb_sysfs.o hugetlb_sysctl.o
 ifdef CONFIG_CMA
 obj-$(CONFIG_HUGETLBFS)	+= hugetlb_cma.o
 endif
diff --git a/mm/hugetlb.c b/mm/hugetlb.c
index 3f6189d2d0188..e87f26a3e1f3e 100644
--- a/mm/hugetlb.c
+++ b/mm/hugetlb.c
@@ -39,6 +39,7 @@
 #include <linux/padata.h>
 #include <linux/pgalloc.h>
 #include <linux/memcontrol.h>
+#include "hugetlb_subpool.h"
 
 #include <asm/page.h>
 #include <asm/tlb.h>
@@ -114,8 +115,7 @@ __cacheline_aligned_in_smp DEFINE_SPINLOCK(hugetlb_lock);
 static int num_fault_mutexes __ro_after_init;
 struct mutex *hugetlb_fault_mutex_table __ro_after_init;
 
-/* Forward declaration */
-static int hugetlb_acct_memory(struct hstate *h, long delta);
+/* Forward declarations */
 static void hugetlb_vma_lock_free(struct vm_area_struct *vma);
 static void hugetlb_vma_lock_alloc(struct vm_area_struct *vma);
 static void __hugetlb_vma_unlock_write_free(struct vm_area_struct *vma);
@@ -126,156 +126,6 @@ static void hugetlb_unshare_pmds(struct vm_area_struct *vma,
 		unsigned long start, unsigned long end, bool take_locks);
 static struct resv_map *vma_resv_map(struct vm_area_struct *vma);
 
-static inline bool subpool_is_free(struct hugepage_subpool *spool)
-{
-	if (spool->count)
-		return false;
-
-	return spool->used_hpages == 0;
-}
-
-static inline void unlock_or_release_subpool(struct hugepage_subpool *spool,
-						unsigned long irq_flags)
-{
-	spin_unlock_irqrestore(&spool->lock, irq_flags);
-
-	/* If no pages are used, and no other handles to the subpool
-	 * remain, give up any reservations based on minimum size and
-	 * free the subpool */
-	if (subpool_is_free(spool)) {
-		if (spool->min_hpages != -1)
-			hugetlb_acct_memory(spool->hstate,
-						-spool->min_hpages);
-		kfree(spool);
-	}
-}
-
-struct hugepage_subpool *hugepage_new_subpool(struct hstate *h, long max_hpages,
-						long min_hpages)
-{
-	struct hugepage_subpool *spool;
-
-	spool = kzalloc_obj(*spool);
-	if (!spool)
-		return NULL;
-
-	spin_lock_init(&spool->lock);
-	spool->count = 1;
-	spool->max_hpages = max_hpages;
-	spool->hstate = h;
-	spool->min_hpages = min_hpages;
-
-	if (min_hpages != -1 && hugetlb_acct_memory(h, min_hpages)) {
-		kfree(spool);
-		return NULL;
-	}
-	spool->rsv_hpages = min_hpages;
-
-	return spool;
-}
-
-void hugepage_put_subpool(struct hugepage_subpool *spool)
-{
-	unsigned long flags;
-
-	spin_lock_irqsave(&spool->lock, flags);
-	BUG_ON(!spool->count);
-	spool->count--;
-	unlock_or_release_subpool(spool, flags);
-}
-
-/*
- * Subpool accounting for allocating and reserving pages.
- * Return -ENOMEM if there are not enough resources to satisfy the
- * request.  Otherwise, return the number of pages by which the
- * global pools must be adjusted (upward).  The returned value may
- * only be different than the passed value (delta) in the case where
- * a subpool minimum size must be maintained.
- */
-static long hugepage_subpool_get_pages(struct hugepage_subpool *spool,
-				      long delta)
-{
-	long ret = delta;
-
-	if (!spool)
-		return ret;
-
-	spin_lock_irq(&spool->lock);
-
-	if (spool->max_hpages != -1 &&
-	    spool->used_hpages + delta > spool->max_hpages) {
-		ret = -ENOMEM;
-		goto unlock_ret;
-	}
-
-	spool->used_hpages += delta;
-
-	/* minimum size accounting */
-	if (spool->min_hpages != -1 && spool->rsv_hpages) {
-		if (delta > spool->rsv_hpages) {
-			/*
-			 * Asking for more reserves than those already taken on
-			 * behalf of subpool.  Return difference.
-			 */
-			ret = delta - spool->rsv_hpages;
-			spool->rsv_hpages = 0;
-		} else {
-			ret = 0;	/* reserves already accounted for */
-			spool->rsv_hpages -= delta;
-		}
-	}
-
-unlock_ret:
-	spin_unlock_irq(&spool->lock);
-	return ret;
-}
-
-/*
- * Subpool accounting for freeing and unreserving pages.
- * Return the number of global page reservations that must be dropped.
- * The return value may only be different than the passed value (delta)
- * in the case where a subpool minimum size must be maintained.
- */
-static long hugepage_subpool_put_pages(struct hugepage_subpool *spool,
-				       long delta)
-{
-	long ret = delta;
-	unsigned long flags;
-
-	if (!spool)
-		return delta;
-
-	spin_lock_irqsave(&spool->lock, flags);
-
-	spool->used_hpages -= delta;
-
-	 /* minimum size accounting */
-	if (spool->min_hpages != -1 && spool->used_hpages < spool->min_hpages) {
-		/*
-		 * limit is the maximum number of reservations that
-		 * can be restored to this subpool.
-		 */
-		long limit = spool->min_hpages - spool->used_hpages;
-
-		if (spool->rsv_hpages + delta <= limit)
-			ret = 0;
-		else
-			ret = spool->rsv_hpages + delta - limit;
-
-		spool->rsv_hpages += delta;
-		if (spool->rsv_hpages > limit)
-			spool->rsv_hpages = limit;
-	}
-
-	/*
-	 * If hugetlbfs_put_super couldn't free spool due to an outstanding
-	 * quota reference, free it now.
-	 */
-	unlock_or_release_subpool(spool, flags);
-
-	return ret;
-}
-
 static inline struct hugepage_subpool *subpool_vma(struct vm_area_struct *vma)
 {
 	return subpool_inode(file_inode(vma->vm_file));
@@ -4602,7 +4452,7 @@ unsigned long hugetlb_total_pages(void)
 	return nr_total_pages;
 }
 
-static int hugetlb_acct_memory(struct hstate *h, long delta)
+int hugetlb_acct_memory(struct hstate *h, long delta)
 {
 	int ret = -ENOMEM;
 
diff --git a/mm/hugetlb_subpool.c b/mm/hugetlb_subpool.c
new file mode 100644
index 0000000000000..b12c16aa7e4c5
--- /dev/null
+++ b/mm/hugetlb_subpool.c
@@ -0,0 +1,168 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Subpool and reserve accounting for HugeTLB folios.
+ * Extracted from mm/hugetlb.c
+ */
+
+#include <linux/types.h>
+#include <linux/kernel.h>
+#include <linux/slab.h>
+#ifdef __KERNEL__
+#include <linux/hugetlb.h>
+#endif
+#include <linux/spinlock.h>
+#include <linux/bug.h>
+
+#include "hugetlb_subpool.h"
+
+static inline bool subpool_is_free(struct hugepage_subpool *spool)
+{
+	if (spool->count)
+		return false;
+
+	return spool->used_hpages == 0;
+}
+
+static inline void unlock_or_release_subpool(struct hugepage_subpool *spool,
+						unsigned long irq_flags)
+{
+	spin_unlock_irqrestore(&spool->lock, irq_flags);
+
+	/*
+	 * If no pages are used, and no other handles to the subpool
+	 * remain, give up any reservations based on minimum size and
+	 * free the subpool.
+	 */
+	if (subpool_is_free(spool)) {
+		if (spool->min_hpages != -1)
+			hugetlb_acct_memory(spool->hstate,
+						-spool->min_hpages);
+		kfree(spool);
+	}
+}
+
+struct hugepage_subpool *hugepage_new_subpool(struct hstate *h, long max_hpages,
+						long min_hpages)
+{
+	struct hugepage_subpool *spool;
+
+	spool = kzalloc_obj(*spool);
+	if (!spool)
+		return NULL;
+
+	spin_lock_init(&spool->lock);
+	spool->count = 1;
+	spool->max_hpages = max_hpages;
+	spool->hstate = h;
+	spool->min_hpages = min_hpages;
+
+	if (min_hpages != -1 && hugetlb_acct_memory(h, min_hpages)) {
+		kfree(spool);
+		return NULL;
+	}
+	spool->rsv_hpages = min_hpages;
+
+	return spool;
+}
+
+void hugepage_put_subpool(struct hugepage_subpool *spool)
+{
+	unsigned long flags;
+
+	spin_lock_irqsave(&spool->lock, flags);
+	BUG_ON(!spool->count);
+	spool->count--;
+	unlock_or_release_subpool(spool, flags);
+}
+
+/*
+ * Subpool accounting for allocating and reserving pages.
+ * Return -ENOMEM if there are not enough resources to satisfy the
+ * request.  Otherwise, return the number of pages by which the
+ * global pools must be adjusted (upward).  The returned value may
+ * only be different than the passed value (delta) in the case where
+ * a subpool minimum size must be maintained.
+ */
+long hugepage_subpool_get_pages(struct hugepage_subpool *spool,
+				      long delta)
+{
+	long ret = delta;
+
+	if (!spool)
+		return ret;
+
+	spin_lock_irq(&spool->lock);
+
+	if (spool->max_hpages != -1 &&
+	    spool->used_hpages + delta > spool->max_hpages) {
+		ret = -ENOMEM;
+		goto unlock_ret;
+	}
+
+	spool->used_hpages += delta;
+
+	/* minimum size accounting */
+	if (spool->min_hpages != -1 && spool->rsv_hpages) {
+		if (delta > spool->rsv_hpages) {
+			/*
+			 * Asking for more reserves than those already taken on
+			 * behalf of subpool.  Return difference.
+			 */
+			ret = delta - spool->rsv_hpages;
+			spool->rsv_hpages = 0;
+		} else {
+			ret = 0;	/* reserves already accounted for */
+			spool->rsv_hpages -= delta;
+		}
+	}
+
+unlock_ret:
+	spin_unlock_irq(&spool->lock);
+	return ret;
+}
+
+/*
+ * Subpool accounting for freeing and unreserving pages.
+ * Return the number of global page reservations that must be dropped.
+ * The return value may only be different than the passed value (delta)
+ * in the case where a subpool minimum size must be maintained.
+ */
+long hugepage_subpool_put_pages(struct hugepage_subpool *spool,
+				       long delta)
+{
+	long ret = delta;
+	unsigned long flags;
+
+	if (!spool)
+		return delta;
+
+	spin_lock_irqsave(&spool->lock, flags);
+
+	spool->used_hpages -= delta;
+
+	 /* minimum size accounting */
+	if (spool->min_hpages != -1 && spool->used_hpages < spool->min_hpages) {
+		/*
+		 * limit is the maximum number of reservations that
+		 * can be restored to this subpool.
+		 */
+		long limit = spool->min_hpages - spool->used_hpages;
+
+		if (spool->rsv_hpages + delta <= limit)
+			ret = 0;
+		else
+			ret = spool->rsv_hpages + delta - limit;
+
+		spool->rsv_hpages += delta;
+		if (spool->rsv_hpages > limit)
+			spool->rsv_hpages = limit;
+	}
+
+	/*
+	 * If hugetlbfs_put_super couldn't free spool due to an outstanding
+	 * quota reference, free it now.
+	 */
+	unlock_or_release_subpool(spool, flags);
+
+	return ret;
+}
diff --git a/mm/hugetlb_subpool.h b/mm/hugetlb_subpool.h
new file mode 100644
index 0000000000000..be1f1cf012c9c
--- /dev/null
+++ b/mm/hugetlb_subpool.h
@@ -0,0 +1,17 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef _MM_HUGETLB_SUBPOOL_H
+#define _MM_HUGETLB_SUBPOOL_H
+
+#include <linux/spinlock.h>
+#include <linux/types.h>
+
+struct hstate;
+struct hugepage_subpool;
+
+struct hugepage_subpool *hugepage_new_subpool(struct hstate *h, long max_hpages,
+						long min_hpages);
+void hugepage_put_subpool(struct hugepage_subpool *spool);
+long hugepage_subpool_get_pages(struct hugepage_subpool *spool, long delta);
+long hugepage_subpool_put_pages(struct hugepage_subpool *spool, long delta);
+
+#endif /* _MM_HUGETLB_SUBPOOL_H */

-- 
2.55.0.229.g6434b31f56-goog